Indian sign language recognition using Krawtchouk moment-based local features

In this paper, Krawtchouk moment-based shape features at lower orders are proposed for Indian sign language (ISL) recognition system which gives local information about the shape from a specific region of interest. The shape recognition capability of Krawtchouk moment-based local features is verified on two databases: the standard Jochen Triesch’s database and 26 ISL alphabets which are collected from 72 different subjects, with variations in position, scale and rotation. Feature selection is performed to minimise redundancy. The effect of order and feature dimensionality for different classifiers is studied. Results show that Krawtchouk moment-based local features are found to exhibit user, scale, rotation and translation invariance. Moreover, they have shape identification capability.     

基于数据生成的手语识别自适应方法

采用自适应技术来解决非特定人手语识别问题,提出了一种基于数据生成的手语识别自适应方法.首先,对非特定人模型的均值向量进行自动聚类,寻找聚类中心生成手语词码本,然后,根据此码本选择词根子集,该子集能覆盖手语词码本的所有码字,继而,使用新用户的词根子集数据通过遗传算法生成其它词根的数据,最后,结合词根子集的真实数据和其它词根的生成数据,利用最大似然线性回归(MLLR)和最大后验概率(MAP)算法对非特定人模型进行自适应.实验结果表明,该方法既能够降低所需要的自适应数据量,又能够在非特定人模型基础上取得识别正确率的大幅提高.     

A novel key-frame selection-based sign language recognition framework for the video data

ABSTRACT

Sign language is a medium of communication for people with hearing disabilities. Static and dynamic gestures are identified in a video-based sign language recognition and translated them into humanly understandable phrases to achieve the communication objective. However, videos contain redundant Key-frames which require additional processing. Number of such Key-frames can be reduced. The selection of particular Key-frames without losing the required information is a challenging task. The Key-frame extraction algorithm is used which helps to speed-up the sign language recognition process by extracting essential key-frames. The proposed framework eliminates the computation overhead by picking up the distinct Key-frames for the recognition process. Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), and Histograms of Oriented Gradient (HOG) are used for unique features extraction. We used the bagged tree, boosted tree ensemble method, Fine KNN, and SVM for classification. We tested methodology on video-based datasets of Pakistani Sign Language. It achieved an overall 97.5% accuracy on 37 Urdu alphabets and 95.6% accuracy on 100 common words.     

Road sign recognition and non-recognition

The problem of non-recognition of road signs has many aspects which are of great importance in traffic safety. Considering all signs on a test road and eye-movement technique and recognition rate method, a temporal analysis has been conducted for two techniques of driving: driving with the time necessary to see, read and recognize each type of road sign, and free driving to determine the actual time the driver spends reading these signs. The actual time spent provides recognition rates, totally and partially, and also rates of non-recognition. Many of the factors involved were investigated and the analysis was designed to estimate the effect of these factors separately. For a more practical use of the results, a set of probabilistic models has been estimated to characterize the different distributions of fixation durations. Next, the parameters of these models were used to develop a method for measuring the efficiency-level index of the road sign system.     

Arabic sign language intelligent translator

ABSTRACT

Arabic sign language (ArSL) is method of communication between deaf communities in Arab countries; therefore, the development of systemsthat can recognize the gestures provides a means for the Deaf to easily integrate into society. In this research we implemented a computational structurefor an intelligent interpreter that automatically recognizes the isolated dynamic gestures. The proposed system recognizes and translates gesturesperformed with one or both hands. It comprises five subsystems, building dataset, video processing, feature extraction, mapping between ArSL and Arabictext, and text generation. To apply the system, 100-signs of ArSL was used, which was applied on 1500 video files. It's were divided into five classes:alphabet, numbers, "prepositions, pronouns and question words", Arabic life expressions, and "nouns and verbs". The evaluation indicated that thesystem automatically recognizes and translates isolated dynamic ArSL gestures by highly accurate manner. The results showed that the system accuracy is 95.8%.     

Automatic speech recognition

Speech recognition, which remained on the fringes of commercial interest for many years, came into prominence recently due to the support extended to this research area by the Advanced Research Projects Agency of theusa. More recently, this area of research has received added impetus due to the priority assigned to the development of fifth generation computers by Japan and several other countries of the world and the importance of speech input/output systems therein. India has a long tradition of good quality work in this area. In this paper, we present a brief overview of different aspects of automatic speech recognition research and present the state-of-the art in this area. We cover the world trends in this area of research, with special attention to work done in India.     

Scale and skew‐invariant road sign recognition

A fast and robust method to detect and recognize scaled and skewed road signs is proposed in this paper. In the detection stage, the input color image is first quantized in HSV color model. Border tracing those regions with the same colors as road signs is adopted to find the regions of interest (ROI). The ROIs are then automatically adjusted to fit road sign shape models so as to facilitate detection verification even for scaled and skewed road signs in complicated scenes. Moreover, the ROI adjustment and verification are both performed only on border pixels; thus, the proposed road sign detector is fast. In the recognition stage, the detected road sign is normalized first. Histogram matching based on polar mesh is then adopted to measure the similarity between the scene and model road signs to accomplish recognition. Since histogram matching is fast and has high tolerance to distortion and deformation while contextual information can still be incorporated into it in a natural and elegant way, our method has high recognition accuracy and fast execution speed. Experiment results show that the detection rate and recognition accuracy of our method can achieve 94.2% and 91.7%, respectively. On an average, it takes only 4–50 and 10 ms for detection and recognition, respectively. Thus, the proposed method is effective, yet efficient. © 2007 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 28–39, 2007     

一种视频图像序列中运动对象的分割与跟踪算法

本文提出了一种视频图像序列中运动对象的分割与跟踪算法。该算法通过Canny算子检测出差帧图像的边缘信息,并结合当前帧与背景帧的边缘图像,提取出运动对象。在后续帧中通过建立前帧感兴趣运动对象与当前帧中各运动对象的帧间向量来跟踪当前帧中感兴趣的视频对象。实验结果表明,该算法可行,而且由于该算法简单、计算复杂度小,能很好地满足实时监控系统中对感兴趣运动对象的提取与跟踪。     

肤色建模和肤色分割的人脸定位研究

为了实现彩色图像中人脸的精确定位,提出了一种基于肤色模型、肤色分割处理的人脸定位算法.通过建立肤色模型计算得到图像的相似度分布图,经自适应阈值的二值化处理后,再进行肤色分割,将非人脸区域去除:最终利用眼睛与嘴巴构成三角形特征结合人脸椭圆模板匹配定位人脸.实验结果表明,该算法对于复杂背景下的彩色图像中的人脸正面定位和人脸转动一定角度后定位都有较好效果.     

Robust traffic sign shape recognition using geometric matching

A novel approach for recognising various traffic sign shapes in outdoor environments is presented.To reduce the influence of digital noise and extract the shape of each individual traffic sign, the external boundaries of traffic signs segmented based on colour information are simplified and decomposed through discrete curve evolution whose stop stage is determined by an arc similarity measure in tangent space. The recognition of a closed candidate shape is achieved through the direct matching with templates. An optimal enclosure is generated to minimise the geometric differences between the retrieved unclosed candidate shape and templates. The experimental results justify that the proposed algorithm is translation, rotation and scaling invariant, and gives reliable shape recognition in complex traffic scenes where clustering and partial occlusion normally occur.     

Automatic segmentation and approximation of digitized data for reverse engineering

Reverse engineering is the process of developing a computer-aided design (CAD) model and a manufacturing database for an existing object. This process is used in CAD modelling of part prototypes, in designing moulds and in automated inspection of parts with a complex surface. This paper reports on the automatic segmentation and approximation of three-dimensional digitized points for reverse engineering. Based on an innovation that uses the properties of a non-uniform rational B-spline (NURBS) or B-spline and makes ordered digitized points be control points directly to construct a NURBS or B-spline surface, which takes less computation time than traditional algorithms in calculating surface normals and curvatures at digitized points, an algorithm was developed for automatic segmentation and NURBS surfaces fitting for digitized points.     

Automatic target recognition using multi-diversity radar

The information content of radar target signatures is a key aspect for automatic target recognition. The role of high-range resolution is investigated as a function of the illuminating wavelength. The classification performance is evaluated using (i) full-scale 2D inverse synthetic aperture radar images obtained from a stepped-frequency chirp modulation radar system and (ii) the corresponding sub-spectra of the target reflectivity function forming lower resolution images at differing centre frequencies. The classification performance as given by different combinations of RF frequencies are also evaluated and compared with the coherent reconstruction from the full bandwidth. Finally, the classification results are also computed using multiple aspects to sense the target. In this way, classification performance as function of diversity space is examined.     

Automatic segmentation of cerebral hemispheres in MR human head scans

Automatic segmentation of cerebral hemispheres in magnetic resonance (MR) brain images help to quantify the brain asymmetry and correct several MR brain deformities. The detection of mid‐sagittal plane (MSP) in human brain image is necessary to segment the hemispheres for both operator‐based and automated brain image asymmetric analysis. In this article, a computationally simple and accurate technique to detect MSP in MRI human head scans using curve fitting is developed. The left and right hemispheres are segmented based on the detected MSP. The accuracy of the MSP is evaluated by comparing the segmented left and right hemispheres against the manually segmented ones. Experimental results using 78 volumes of T1, T2 and PD‐weighted MRI brain images show that the proposed method has accurately segmented the cerebral hemispheres based on the detected MSP in axial and coronal orientations of normal and pathological brain images.     

Nearest neighbour classification of Indian sign language gestures using kinect camera

People with speech disabilities communicate in sign language and therefore have trouble in mingling with the able-bodied. There is a need for an interpretation system which could act as a bridge between them and those who do not know their sign language. A functional unobtrusive Indian sign language recognition system was implemented and tested on real world data. A vocabulary of 140 symbols was collected using 18 subjects, totalling 5041 images. The vocabulary consisted mostly of two-handed signs which were drawn from a wide repertoire of words of technical and daily-use origins. The system was implemented using Microsoft Kinect which enables surrounding light conditions and object colour to have negligible effect on the efficiency of the system. The system proposes a method for a novel, low-cost and easy-to-use application, for Indian Sign Language recognition, using the Microsoft Kinect camera. In the fingerspelling category of our dataset, we achieved above 90% recognition rates for 13 signs and 100% recognition for 3 signs with overall 16 distinct alphabets (A, B, D, E, F, G, H, K, P, R, T, U, W, X, Y, Z) recognised with an average accuracy rate of 90.68%.     

Automatic recognition of welding defects in real-time radiography

This paper describes a real-time radiography configuration for the automatic inspection of welds. The optimal geometrical imaging configuration is evaluated and discussed in relation to conventional film radiography. For the automatic inspection of X-ray images, a two-step analysis was adopted: a fast search for defective regions, followed by fine identification and location of defects. Two different algorithms, based on the relative irregular behaviour of a defect, were developed for the fast search procedure. The second step, fine identification, can be achieved by a sequential similarity detection algorithm or by a thresholding algorithm. The different methods were applied to various X-ray images of welds and the automatic inspection was evaluated and compared with visual inspection.     

中华白海豚回声定位信号自动识别

中华白海豚是我国一级保护动物,以往研究表明不同海域中华白海豚的回声定位(click)信号存在差异。文章以回声定位信号为识别标准,使用三种机器学习方法(K近邻法,决策树-分类回归树法和朴素贝叶斯法)识别中华白海豚。首先使用Teager-Kaiser能源算子(Teager-Kaiser Energy Operator, TKEO)方法和Gabor滤波器进行中华白海豚click信号的自动检测,然后通过倒谱的方法提取click信号的特征,最后利用3种机器学习方法识别中华白海豚。实验数据采集于雷州湾的中华白海豚以及厦门湾的中华白海豚和宽吻海豚的发声信号。实验中将厦门湾中华白海豚和雷州湾中华白海豚设为第一组,进行同种海豚识别;将厦门海域中华白海豚和宽吻海豚设为第二组,进行不同种海豚识别,实验结果表明这两组实验的平均识别准确率分别可以达到98%和96%。     

Automatic target recognition employing signal compression

Quadratic correlation filters (QCFs) have been used successfully to detect and recognize targets embedded in background clutter. Recently, a QCF called the Rayleigh quotient quadratic correlation filter (RQQCF) was formulated for automatic target recognition (ATR) in IR imagery. Using training images from target and clutter classes, the RQQCF explicitly maximized a class separation metric. What we believe to be a novel approach is presented for ATR that synthesizes the RQQCF using compressed images. The proposed approach considerably reduces the computational complexity and storage requirements while retaining the high recognition accuracy of the original RQQCF technique. The advantages of the proposed scheme are illustrated using sample results obtained from experiments on IR imagery.     

Connected digit speech recognition system for Malayalam language

A connected digit speech recognition is important in many applications such as automated banking system, catalogue-dialing, automatic data entry, automated banking system, etc. This paper presents an optimum speaker-independent connected digit recognizer for Malayalam language. The system employs Perceptual Linear Predictive (PLP) cepstral coefficient for speech parameterization and continuous density Hidden Markov Model (HMM) in the recognition process. Viterbi algorithm is used for decoding. The training data base has the utterance of 21 speakers from the age group of 20 to 40 years and the sound is recorded in the normal office environment where each speaker is asked to read 20 set of continuous digits. The system obtained an accuracy of 99.5 % with the unseen data.     

一种新的基于区域的高速公路多车辆跟踪方案

提出一种新的基于区域的高速公路多车辆跟踪方案,包括背景建模、目标识别、目标跟踪等过程。针对高速公路监控图像质量差和干扰信号强的特点,在常规的颜色混合高斯背景模型的基础上,提出一种新的基于扰动区域的高斯背景模型来消除强噪声和背景小幅度运动的影响,并在时间序列上通过Kalman滤波迭代加权算法实现背景模型的自适应性更新。该背景模型明显提高了背景分割的准确性和自适应性。提出了一种改进的非递归区域生长算法用以有效地实现多目标的识别,算法复杂度仅为O(n)。采用目标特征匹配和区域运动预测规则对多车辆进行实时跟踪和识别。实现了一个高速公路实时监控原型系统,运行结果表明,该跟踪方法不仅能准确跟踪和识别多目标,而且对道路环境和车辆运动方向具有很好的适应性和鲁棒性。